Import Documents sanitizes pdfs

biolab · Jun 7, 2019 · 1cb10e2 · 1cb10e2
1 parent 6020e1b
commit 1cb10e2
Showing 1 changed file with 1 addition and 2 deletions.
diff --git a/orangecontrib/text/import_documents.py b/orangecontrib/text/import_documents.py
@@ -138,8 +138,7 @@ def read_file(self):
             for lt_obj in layout:
                 if isinstance(lt_obj, LTTextBox) or isinstance(lt_obj, LTTextLine):
                     extracted_text.append(lt_obj.get_text())
-        self.content = ' '.join(extracted_text)
-
+        self.content = ' '.join(extracted_text).replace('\x00', '')
 
 class XmlReader(Reader):
     ext = [".xml"]